AI Glossary

Have more questions? Submit a request

When you use Voicehub, you're already getting all the speed and accuracy of Rev's best-in-class AI speech recognition (ASR) engine. Although our ASR engine has a dictionary of more than 500,000 words, it can sometimes fail to recognize niche or industry-specific terminology and proper nouns.

To address this problem, Voicehub has a Glossary feature, which allows you to improve transcription accuracy by supplying a custom list of words, phrases, or terms to the ASR engine. Glossary items can be easily added to your account at any time and will be used by the ASR engine on all subsequent AI transcription orders.

 

Getting Started

To start using the Glossary, log in to your Rev account and navigate to Manage Glossary by opening the menu on the top right next to your name and expanding the resources section. 

Enter one or more words, phrases, or terms in the Glossary Terms box adding only one word, phrase, or term per line.

 

Click Save once you're done. Subsequent AI transcription orders will use the contents of the Glossary during the speech recognition process.

 

Working with the Glossary

The following limitations currently apply to the Glossary:

  • Maximum 1000 phrases
  • Maximum 5 words per phrase, separated by a space
  • Maximum 34 characters per word
  • Only English letters, spaces, hyphens and apostrophes supported

 

The Glossary also includes two useful features to make data entry easier and error-free:

  • You can paste a multi-line text block into the editor and the editor will automatically format it for use, including removing empty lines and splitting comma-separated phrases.
  • All words and phrases entered into the editor are automatically validated and errors are highlighted with an `!` icon. You can click the `!` icon to see a description of the error.

 

Updating the Glossary

The Glossary is persistent and the items in the Glossary apply to all your transcription orders. You can update the Glossary at any time to add, modify, or delete entries. To do so, follow the same steps above to navigate to the Glossary terms, edit the existing terms in the box, and then Save

 

Glossary Best Practices

To achieve the best transcription results possible with the Glossary, follow these recommendations.

 

Uniqueness

The Glossary is intended only for special or unusual words and phrases. Examples of such terms include made-up words or words with unique spelling such as sparkletini, yulg, or Dave Zsykpo. Examples of bad custom vocabulary terms are Google, lorem ipsum, or orthostatic hypotension.

 

Significance

Add only important or key terms to the Glossary so that the list stays short (no more than 500 phrases). Long lists may negatively impact performance and accuracy. Remember that you can always update the Glossary to include additional words that you consider important.

 

Length

The Glossary limits you to 5 words per phrase because performance degrades past this number. Keep phrases as short as possible. For example, instead of the phrase "increasing awareness of outside influence", use the shorter phrase "outside influence".

 

Review

Review the Glossary periodically to remove terms that are no longer relevant and to add new terms based on your changing requirements. If you start to see increased errors after adding a large number of new terms to the Glossary, reduce the number of terms to the most important ones.

Was this article helpful?
0 out of 0 found this helpful